Training in progress, step 3980, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb92eeee4f10b88452adab2b86e02b1a55219a9a903898c13345aafea5b652bf
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:129b12ef463c9b415d145e672db9245320c03f48bd1109f0b8d857667b334fea
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e00055690825dfa08ac78e1506244a3a8ef6c7831d00d7a6c1a46e128b78da37
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44f219189445926df0babc469312f611e8c019ba4849565af1d4190bf43f3386
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3988,6 +3988,16 @@
|
|
| 3988 |
"mean_token_accuracy": 0.7604210332036019,
|
| 3989 |
"num_tokens": 18508661.0,
|
| 3990 |
"step": 3970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3991 |
}
|
| 3992 |
],
|
| 3993 |
"logging_steps": 10,
|
|
@@ -4007,7 +4017,7 @@
|
|
| 4007 |
"attributes": {}
|
| 4008 |
}
|
| 4009 |
},
|
| 4010 |
-
"total_flos": 8.
|
| 4011 |
"train_batch_size": 4,
|
| 4012 |
"trial_name": null,
|
| 4013 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8490666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3988 |
"mean_token_accuracy": 0.7604210332036019,
|
| 3989 |
"num_tokens": 18508661.0,
|
| 3990 |
"step": 3970
|
| 3991 |
+
},
|
| 3992 |
+
{
|
| 3993 |
+
"entropy": 1.056539323925972,
|
| 3994 |
+
"epoch": 0.8490666666666666,
|
| 3995 |
+
"grad_norm": 0.24575304985046387,
|
| 3996 |
+
"learning_rate": 6.464874175025602e-05,
|
| 3997 |
+
"loss": 1.1153278350830078,
|
| 3998 |
+
"mean_token_accuracy": 0.7435829386115074,
|
| 3999 |
+
"num_tokens": 18560510.0,
|
| 4000 |
+
"step": 3980
|
| 4001 |
}
|
| 4002 |
],
|
| 4003 |
"logging_steps": 10,
|
|
|
|
| 4017 |
"attributes": {}
|
| 4018 |
}
|
| 4019 |
},
|
| 4020 |
+
"total_flos": 8.787590296359936e+16,
|
| 4021 |
"train_batch_size": 4,
|
| 4022 |
"trial_name": null,
|
| 4023 |
"trial_params": null
|